Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

BINK: Biological binary keypoint descriptor.

Mário Saleiro1, Kasim Terzić2, J M F Rodrigues1

  • 1Vision Laboratory, LARSyS, FCT & ISE, University of the Algarve, Faro, Portugal.

Bio Systems
|October 17, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Automatic detection of fish scale circuli using deep learning.

Biology methods & protocols·2024
Same author

Data-Driven Robotic Manipulation of Cloth-like Deformable Objects: The Present, Challenges and Future Prospects.

Sensors (Basel, Switzerland)·2023
Same author

Re-identification of individuals from images using spot constellations: a case study in Arctic charr (<i>Salvelinus alpinus</i>).

Royal Society open science·2021
Same author

Development and Testing of a Dual Accelerometer Vector Sensor for AUV Acoustic Surveys.

Sensors (Basel, Switzerland)·2017
Same author

Proto-object categorisation and local gist vision using low-level spatial features.

Bio Systems·2015
Same author

Multi-scale keypoints in V1 and beyond: object segregation, scale selection, saliency maps and face detection.

Bio Systems·2006

Researchers developed BINK, a novel biologically inspired binary keypoint descriptor. This new method, based on cortical V1 cell responses, significantly improves performance over existing biologically inspired approaches for computer vision tasks.

Area of Science:

  • Computer Vision
  • Computational Neuroscience
  • Machine Learning

Background:

  • Keypoint descriptors are crucial for matching local features in computer vision and biological vision.
  • Existing floating-point descriptors (e.g., SIFT, SURF) offer high matching rates but are computationally intensive.
  • Binary descriptors offer speed advantages for real-time applications and resource-constrained devices, but biologically inspired methods lag in performance.

Purpose of the Study:

  • To introduce a novel biologically inspired binary keypoint descriptor named BINK.
  • To enhance the performance of biologically inspired descriptors for computer vision tasks.
  • To provide a descriptor suitable for real-time applications and integration with existing V1-based systems.

Main Methods:

Keywords:
ApplicationsBio-inspiredCortical cellsDescriptorKeypoints

Related Experiment Videos

  • Developed BINK based on the responses of cortical V1 cells.
  • Evaluated BINK's performance against other biologically inspired and computational descriptors.
  • Demonstrated the descriptor's compatibility with a previously developed V1-based keypoint detector.

    • Main Results:

    • BINK significantly outperforms existing biologically inspired keypoint descriptors.
    • The descriptor achieves high matching rates while maintaining computational efficiency.
    • BINK shows potential for real-time computer vision applications.

    Conclusions:

    • BINK represents a significant advancement in biologically inspired binary keypoint descriptors.
    • The descriptor offers a compelling alternative for applications requiring fast and accurate local feature matching.
    • Integration with V1-based keypoint detection enables efficient, real-time visual processing.